Authenticity determination device and program

Abstract

To provide an authenticity determination device and others, capable of suitable authenticity determination for a personal certificate.SOLUTION: An authenticity determination device 3 determines authenticity of an ID card having a face image formed thereon. The authenticity determination device 3 includes: reception means 301 that receives an image of an ID card from a user terminal 5; and authenticity determination means 302 that determines whether or not a printed matter is stuck onto a background area of the face image on the basis of a result of edge detection for the image of the ID card, and when it is determined that the printed matter is stuck onto the background area, determines the ID card as false.SELECTED DRAWING: Figure 4

Description

Technical Field

[0001] The present invention relates to a forgery determination device and its program.

Background Art

[0002] Financial institutions require identity verification using an ID card (personal identification certificate) such as a My Number card when opening an account. However, cases of forging or altering ID cards are increasing in order to impersonate someone else for criminal purposes such as fraud.

[0003] In ordinary financial institutions, it is common for a user to visit the financial institution and submit an ID card, and the financial institution side conducts face-to-face identity verification using the submitted ID card. In this case, the ID card can be carefully observed, and unnaturalness can also be detected by the tactile sensation of the card.

[0004] Also, Patent Documents 1 and 2 describe a forgery determination device that determines the authenticity of an ID card from an image obtained by reading the face of the ID card with a reading device such as a scanner, and it is also possible to determine the authenticity of the ID card by reading the submitted ID card with a reading device such as a scanner.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0006] Recently, financial institutions on the Internet such as online banks have become common. In this type of financial institution, some perform identity verification by taking a picture of the face of an ID card with a camera such as a smartphone and sending the image to the financial institution.

[0007] In this case, identity verification is performed solely through images rather than in person, so measures to detect forged or altered fake ID cards are desired. However, detecting fake ID cards from images alone is not easy, which has been a challenge in online applications and other processes.

[0008] For example, regarding the facial image on an ID card, if a fake image of the face is printed on a printed sheet and attached to the ID card to alter it, the fake ID card can be easily detected through face-to-face verification. However, if identity verification is based solely on the image on the ID card, it is not easy to detect the fake.

[0009] The present invention has been made in view of the above-mentioned problems, and aims to provide a genuineness determination device, etc., that can suitably determine the authenticity of an identity verification document. [Means for solving the problem]

[0010] The first invention for solving the aforementioned problems is an authenticity determination device for an identification document on which a facial image is formed, comprising an authenticity determination means that determines whether or not printed material has been attached to the background area of ​​the facial image based on the result of edge detection performed on the image of the identification document, and determines that the identification document is fake if it is determined that printed material has been attached to the background area of ​​the facial image, wherein the authenticity determination means calculates an edge value indicating the magnitude of the change in brightness of pixels in the direction crossing the contour portion of the image in the range of the image that crosses the contour portion of the background area, uses the maximum value of the absolute value of the edge value as the determination value, and performs the determination by comparing the determination value with a threshold. The second invention is an authenticity determination device for an identification document on which a facial image is formed, comprising: an authenticity determination means that determines whether or not printed material has been attached to the background area of ​​the facial image based on the result of edge detection performed on the image of the identification document, and determines that the identification document is fake if it is determined that printed material has been attached to the background area of ​​the facial image, wherein the authenticity determination means calculates an edge value indicating the magnitude of the change in brightness of pixels in the direction crossing the contour portion of the image in the range of the image crossing the contour portion of the background area, and performs the determination using the edge value, wherein the authenticity determination means compares the brightness of both ends in the direction crossing the contour portion of the image in the range of the image crossing the contour portion of the background area, and based on the comparison result, decides whether to use the edge value indicating that the brightness increases toward one of the ends for the determination, or the edge value indicating that the brightness decreases toward the end for the determination. 。

[0011] When an identity verification document is altered by pasting a piece of paper or other printed material with a fake face image onto the background area of ​​the face image, dark or bright lines appear in the image of the identity verification document due to the unevenness of the printed material. By detecting these dark or bright lines using edge detection techniques, the altered identity verification document can be suitably determined to be a fake identity verification document.

[0012] In the first invention The authenticity determination means uses the maximum absolute value of the edge value as the discrimination value and performs the determination by comparing the discrimination value with a threshold value. More specifically, regarding the image of the identification document, an image of the area crossing the contour of the background region of the face image can be extracted, and the magnitude of the brightness change of pixels along that crossing direction can be used as the edge value for the aforementioned discrimination. For example, the dark lines and bright lines mentioned above appear as the maximum value of the absolute value of the edge value, so this maximum value can be used as the discrimination value, and the discrimination value can be compared with a threshold value.

[0013] In the second invention,The authenticity determination means compares the brightness of both ends in the direction crossing the contour portion of the background region with respect to the image in the area crossing the contour portion, and based on the comparison result, decides whether to use the edge value that indicates the brightness increases toward one of the ends for the determination, or the edge value that indicates the brightness decreases toward the other end for the determination. ru. This allows for accurate authentication by avoiding the influence of the boundary between the base color area and the background area of ​​the card material.

[0014] The authenticity determination device preferably has a receiving means for receiving an image of the identity verification document from the user terminal. This makes it possible to build a network-based system that uses images of identification documents sent from a user's terminal to determine their authenticity.

[0015] The 3 The invention is a program for a computer to function as an authenticity determination device for an identification document on which a facial image is formed, comprising: an authenticity determination means that determines whether or not printed material has been attached to the background area of ​​the facial image based on the result of edge detection performed on the image of the identification document, and determines that the identification document is fake if it is determined that printed material has been attached to the background area of ​​the facial image, wherein the authenticity determination means calculates an edge value indicating the magnitude of the change in brightness of pixels in the direction crossing the contour portion of the image in the range of the image that crosses the contour portion of the background portion, uses the maximum value of the absolute value of the edge value as the determination value, and performs the determination by comparing the determination value with a threshold value. The 4The invention is an authenticity determination device for personal authentication in which a face image is formed, and based on the result of edge detection performed on the image of the personal authentication, it determines whether a printed matter is pasted on the background area of the face image. When it is determined that a printed matter is pasted on the background area of the face image, it has authenticity determination means for determining that the personal authentication is fake. The authenticity determination means calculates an edge value indicating the magnitude of the brightness change of pixels in the direction crossing the contour portion of the background area for an image in the range crossing the contour portion of the background area, and performs the determination using the edge value. The authenticity determination means compares the brightnesses of both ends in the direction crossing the contour portion for an image in the range crossing the contour portion of the background area, and based on the comparison result, determines whether to use the edge value indicating that the brightness increases toward one of the both ends for the determination, or whether to use the edge value indicating that the brightness decreases toward the one for the determination. It is a program for causing a computer to function as an authenticity determination device characterized by this. 。

Advantages of the Invention

[0016] According to the present invention, it is possible to provide an authenticity determination device or the like that can suitably perform the authenticity determination of personal authentication.

Brief Explanation of the Drawings

[0017] [Figure 1] A diagram showing the authenticity determination system 1. [Figure 2] A diagram showing the hardware configuration of the authenticity determination device 3. [Figure 3] A diagram showing the hardware configuration of the user terminal 5. [Figure 4] A block diagram showing the functions of the authenticity determination device 3. [Figure 5] A diagram showing the ID card 10. [Figure 6] A flowchart showing the outline of the processing of the authenticity determination system 1. [Figure 7] An example of the shooting screen of the ID card 10. [Figure 8] An example of a fake ID card 10. [Figure 9] A flowchart showing the procedure for determining authenticity. [Figure 10] This figure shows the dark line D in brightness image 100 and the regions r2 and r3 at both ends. [Figure 11] A diagram explaining edge value e and mean(e). [Figure 12] A diagram illustrating the edge detection mode. [Figure 13] A diagram showing the ranges r1' and r4. [Modes for carrying out the invention]

[0018] Preferred embodiments of the present invention will be described in detail below with reference to the drawings.

[0019] (1. Authenticity Determination System 1) Figure 1 shows a counterfeit detection system 1 having a counterfeit detection device 3 according to an embodiment of the present invention. The counterfeit detection system 1 is configured by connecting the counterfeit detection device 3 and a user terminal 5 so that they can communicate via a network. In the counterfeit detection system 1, an image of the user's ID card 10 is transmitted from the user terminal 5 to the counterfeit detection device 3, and the counterfeit detection device 3 performs a counterfeit detection of the ID card 10 from the image.

[0020] Figure 2 shows the hardware configuration of the authenticity determination device 3. The authenticity determination device 3 can be implemented by a computer configured by connecting a control unit 31, a storage unit 32, a communication unit 33, etc., via a bus or the like. However, it is not limited to this, and various configurations can be taken as appropriate, and it is also possible to implement the authenticity determination device 3 using multiple computers.

[0021] The control unit 31 consists of a CPU, ROM, RAM, etc. The CPU calls and executes programs related to the processing of the authenticity determination device 3, which are stored in storage media such as the memory unit 32 and ROM, into a work area on the RAM. ROM is a non-volatile memory that permanently holds programs and data such as the boot program and BIOS. RAM is a volatile memory that temporarily holds programs and data loaded from the memory unit 32, ROM, etc., and also has a work area used by the control unit 31 to perform various processes.

[0022] The memory unit 32 is a hard disk drive, solid-state drive, flash memory, etc., and stores the program that the authenticity determination device 3 executes during the processing described later, the data necessary for program execution, the OS, etc.

[0023] The communication unit 33 is a communication interface that mediates communication over the network and communicates with the user terminal 5.

[0024] User terminal 5 is a device owned by the user that takes a picture of the ID card 10 and transmits the captured image to the authenticity verification device 3. For example, a smartphone or tablet device can be used as user terminal 5.

[0025] Figure 3 shows the hardware configuration of the user terminal 5. As shown in Figure 3, the user terminal 5 is configured by connecting a control unit 51, a storage unit 52, a display unit 53, an input unit 54, a communication unit 55, a camera 56, an audio input / output unit 57, etc., via a bus or the like. However, it is not limited to this, and various configurations can be taken as appropriate.

[0026] The control unit 51, storage unit 52, and communication unit 55 are substantially the same as the control unit 31, storage unit 32, and communication unit 33 described above. The display unit 53 has a display device such as a liquid crystal panel, and a touch panel is provided as an input unit 54 for inputting to the user terminal 5. The audio input / output unit 57 is equipped with a microphone and speaker used for audio input and output.

[0027] Camera 56 is an area camera composed of an optical lens, an image sensor such as a CCD (Charge Coupled Device) or CMOS (Complementary Metal-Oxide Semiconductor), and an A / D (Analog / Digital) conversion unit. Camera 56 receives the subject image input via the optical lens, converts it photoelectrically using the image sensor to generate an analog image signal, and then converts the analog image signal into digital image data using the A / D conversion unit.

[0028] Figure 4 is a block diagram showing the functions of the authenticity determination device 3. The authenticity determination device 3 includes a receiving means 301, an authenticity determination means 302, etc.

[0029] The receiving means 301 is a system in which the control unit 31 of the authenticity determination device 3 receives an image of the ID card 10 from the user terminal 5 via the communication unit 33.

[0030] The authenticity determination means 302 is a mechanism in which the control unit 31 of the authenticity determination device 3 uses an image of the ID card 10 received from the user terminal 5 to determine the authenticity of the ID card 10. Details of this authenticity determination will be described later.

[0031] (2. ID card 10) ID card 10 is an identity verification document that is subject to authenticity determination in this embodiment. An identity verification document refers to a medium used for identity verification by financial institutions, mobile phone carriers, various government agencies, etc., and in this embodiment, it is a My Number Card.

[0032] Figure 5 is a schematic diagram of ID card 10 (My Number Card), showing a simplified representation of the actual ID card 10 with some details omitted.

[0033] Various pieces of information are printed on the surface of the ID card 10. For example, in the case of a My Number Card, the user's facial image 101, name, address, date of birth, expiration date, etc., are formed on the card base material as information on the card surface.

[0034] Of these, the face image 101 is formed with a rectangular region R as the background, but the contour portion of this background region R is shaded, and this contour portion has a gradient of brightness.

[0035] (3. Outline of the processing of the authenticity determination system 1) Figure 6 is a flowchart illustrating the processes performed by the authenticity determination system 1. In Figure 6, S1-S2 and S7-S8 are processes executed by the control unit 51 of the user terminal 5, which controls various parts of the user terminal 5, while S3-S6 are processes executed by the control unit 31 of the authenticity determination device 3, which controls various parts of the authenticity determination device 3.

[0036] In this embodiment, the user first operates the user terminal 5 to launch a dedicated application program pre-stored in the storage unit 52. The user terminal 5 then displays a menu screen (not shown) on the display unit 53, and activates the camera 56 according to the user's selection on the menu screen to photograph the surface of the ID card 10 (S1).

[0037] Figure 7 shows an example of the screen for capturing the ID card 10 at this time. In this embodiment, when the camera is activated, instructions are displayed on the display unit 53 of the user terminal 5 to prompt the user to place the ID card 10 within a predetermined frame 531, and the ID card 10 is then photographed.

[0038] The user terminal 5 transmits the image obtained by photographing the ID card 10 to the authenticity determination device 3 (S2). This image is a color image (RGB image) in which the color of each pixel is determined by the gradation values ​​of the R (red), G (green), and B (blue) components.

[0039] The authenticity determination device 3 receives an image of the ID card 10 (S3) and uses the image of the ID card 10 to determine its authenticity (S4). Details of the authenticity determination method will be described later.

[0040] If the authenticity determination device 3 determines that the ID card 10 is fake (S5; NO), it transmits a message to the user terminal 5 indicating that the ID card 10 is fake (S6). When the user terminal 5 receives the message that the ID card 10 is fake (S7), it displays this on the display unit 53 (S8) and terminates the process.

[0041] On the other hand, if the authenticity determination device 3 determines that the ID card 10 is genuine (S5; YES), it completes the authenticity determination process. For example, when authenticity determination is performed as identity verification when opening an account at an online financial institution, after the authenticity determination process, the user information (such as name and date of birth) on the surface of the ID card 10 is obtained from the image of the ID card 10 as information necessary for opening the account, registered, and stored in the storage unit 52.

[0042] (4. Authenticity verification of ID card 10) As described above, the contour area R of the background region of the face image 101 on the ID card 10 has a brightness gradient, with the brightness gradually increasing or decreasing. On the other hand, as shown in Figure 8(a), if a counterfeit ID card 10 is created by pasting a printed item 102, such as a piece of paper with a false face image 101 printed on it, the step in the printed item 102 shown in Figure 8(b) will cause linear areas that are darker than the surrounding area (hereinafter referred to as dark lines) or linear areas that are brighter than the surrounding area (hereinafter referred to as bright lines) to appear in the image of the ID card 10, depending on the lighting environment at the time of shooting. Therefore, by finding these dark lines or bright lines that appear in the step in the image of the ID card 10, it is possible to determine whether the ID card 10 is a fake.

[0043] Figure 9 is a flowchart showing the procedure for determining the authenticity of ID card 10 in S4 of Figure 6.

[0044] In this embodiment, the authenticity determination device 3 first extracts an inspection image from the image of the ID card 10 that crosses the contour portion of the background area R of the face image 101 (S401). This range is predetermined according to the position of the background area R on the ID card 10. The symbol r1 in Figures 5 and 8(a) is an example of this range, and is set to the left contour portion, crossing that contour portion in the left-right direction.

[0045] Next, the authenticity determination device 3 converts the inspection image to a predetermined resolution (S402). Resolution conversion can be performed using known methods such as the bilinear method. Resolution conversion is performed as needed and may be omitted in some cases.

[0046] Furthermore, the authenticity determination device 3 obtains a brightness image from the inspection image by converting the brightness of the inspection image after resolution conversion (S403). This conversion obtains a grayscale image (brightness image) based on the brightness value of each pixel by taking the largest gradation value among the gradation values ​​of the R, G, and B components of each pixel in the inspection image as the brightness value of that pixel.

[0047] Figure 10(a) is an example of a brightness image 100 obtained in S403, which is a grayscale image in which pixels with high brightness values ​​are white and pixels with low brightness values ​​are black. In the example of Figure 10(a), a modification has been performed in which a printed material 102 is pasted onto the background area R, as shown in Figure 8(a), and dark lines D appear in the image.

[0048] The authenticity determination device 3 then determines the edge detection mode of the brightness image 100 (S404). The edge detection mode determines which of the positive edge values, negative edge values, or neutral edge values ​​will be used for discrimination in S406, which will be described later. Edge values ​​and their positive and negative values ​​will be described later. Hereafter, each case will be referred to as the positive edge mode, negative edge mode, and normal edge mode, respectively.

[0049] In this embodiment, in S404, the brightness of both ends of the brightness image 100 in the left-right direction is compared. The specific method is not limited, but as an example, the average brightness of all pixels in the leftmost region r2 of the brightness image 100, as illustrated in Figure 10(b), and the average brightness of all pixels in the rightmost region r3 are calculated, and the two values ​​are compared.

[0050] The positions of regions r2 and r3 can be predetermined at specific locations within the brightness image 100, but they can also be set variably using a criterion for brightness uniformity. For example, by changing the position of region r2 (r3) and comparing the maximum and minimum brightness values ​​of pixels within region r2 (r3) at each position, it is possible to set the position of region r2 (r3) when the difference between them is less than or equal to a criterion value.

[0051] The authenticity determination device 3 determines the positive edge mode, negative edge mode, and normal edge mode based on the results of comparing the brightness of both ends of the brightness image 100 in the left-right direction.

[0052] In this embodiment, as shown in equation (1) below, if the value obtained by subtracting the average brightness AR of the rightmost region r3 from the average brightness AL of the leftmost region r2 of the brightness image 100 is greater than a constant value modeTH, it is determined to be a positive edge mode. As shown in equation (2) below, if the value obtained by subtracting the average brightness AL from the average brightness AR is greater than a constant value modeTH, it is determined to be a negative edge mode. On the other hand, as shown in equation (3) below, if the absolute value abs(AL-AR), which is the difference between the average brightness AL and AR, is less than or equal to a constant value modeTH, it is determined to be a normal edge mode. The constant value modeTH can be set in advance according to the condition of the surface of the ID card 10. AL-AR>modeTH…(1) AR-AL>modeTH…(2) abs(AL-AR)≦modeTH…(3)

[0053] The authenticity detection device 3 then performs edge detection on the brightness image 100 (S405). The method of edge detection is not particularly limited, but in this embodiment, as shown in equation (4) below, the brightness value Vn of each pixel in a certain range centered on the pixel of interest in the brightness image 100 is multiplied by a coefficient kn (weighting coefficient) corresponding to the position of each pixel to calculate the sum Σ(Vn×kn), and the sum Σ(Vn×kn) is taken as the edge value e of the pixel of interest. e = Σ(Vn × kn) ... (4)

[0054] Figure 11(a) shows an example of a matrix M (edge ​​detection filter) with the coefficient kn described above, where the center of matrix M corresponds to the position of the pixel P of interest. Furthermore, since the coefficients in the leftmost column of matrix M are negative and the coefficients in the rightmost column are positive, an increase in brightness toward the rightmost edge of brightness image 100 (one of the left and right ends of brightness image 100) is indicated by a positive edge value e, and a decrease in brightness toward the rightmost edge is indicated by a negative edge value e. The absolute value of the edge value e indicates the magnitude of these brightness changes.

[0055] In S405, the edge value e is calculated by treating each pixel of the brightness image 100 as the pixel of interest P. The edge value e obtained for each pixel is averaged among the pixels arranged vertically, and the resulting edge value mean(e) is used for discrimination described later. Figure 11(b) is a graph showing the edge value mean(e) of the brightness image 100.

[0056] Next, the authenticity determination device 3 determines whether or not the printed material 102 has been attached to the background area R based on the edge value mean(e) (S406).

[0057] In other words, when the printed material 102 is attached to the background area R, dark lines D (see Figure 10(a)) or bright lines appear in the brightness image 100, and the absolute value of the edge value mean(e) increases at that location. On the other hand, in the case of a positive ID card 10 without the printed material 102 attached, the absolute value of the edge value mean(e) does not increase due to the gradation of the contour portion of the background area R. Therefore, it is possible to determine whether or not the printed material 102 is attached to the background area R based on the magnitude of the absolute value of the edge value mean(e).

[0058] In S406, the authenticity determination device 3 determines the discrimination value according to the edge detection mode determined in S404. In the case of positive edge mode, it uses the maximum absolute value of the positive edge value mean(e) as the discrimination value. In the case of negative edge mode, it uses the maximum absolute value of the negative edge value mean(e) as the discrimination value. In the case of normal edge mode, it uses the maximum absolute value of the edge value mean(e), regardless of whether it is positive or negative, as the discrimination value.

[0059] Then, the discriminant value is compared with a predetermined threshold, and if the discriminant value is smaller than the threshold, it is determined that the printed material 102 is not attached to the background area R (S406; NO), and the ID card 10 is true as shown in Figure 5 (S407), and the process is terminated. The threshold can be set in advance, taking into consideration the discriminant accuracy, etc.

[0060] On the other hand, if the discrimination value exceeds the threshold, it is determined that the printed material 102 has been attached to the background area R (S406; YES), and the ID card 10 is a fake ID card 10 as shown in Figure 8(a) (S408), and the process is terminated.

[0061] The reason for changing the discrimination value used in S406 according to the edge detection mode determined in S404 is to take into consideration discrimination accuracy, etc.

[0062] In other words, when dark lines or bright lines are present in the brightness image 100, large values ​​appear in both positive and negative directions in the edge value mean(e), as shown in Figure 12(a). In contrast, in the case of a positive ID card 10 and positive edge mode, as shown in the graph of brightness V and edge value mean(e) in Figure 12(b), the brightness V gradually decreases towards the right edge of the brightness image 100, and the edge value mean(e) is basically a negative value. Therefore, determining the presence or absence of dark lines or bright lines in the brightness image 100 using the positive edge value mean(e) of the positive and negative edge values ​​means(e) is preferable in terms of accuracy and ease of threshold setting, as it avoids the influence of the boundary between the base color region of the card substrate and the background region R.

[0063] In negative edge mode, the mean(e) edge value of the brightness image 100 of the positive ID card 10 is basically a positive value, the opposite of the above. Therefore, it is preferable to determine the presence or absence of dark lines or bright lines in the brightness image 100 using the negative edge value mean(e) among the positive and negative edge values ​​mean(e). On the other hand, there are cases where it is not possible to determine whether it is positive edge mode or negative edge mode (normal edge mode), but in such cases, the absolute value of the edge value mean(e), regardless of whether it is positive or negative, can be used for determination.

[0064] As described above, in this embodiment, when an alteration is performed by pasting a printed material 102, such as a piece of paper with a fake face image 101 printed on it, onto the background area R of the face image 101 of the ID card 10, dark lines or bright lines appear in the image of the ID card 10 due to the unevenness of the printed material 102. By detecting these dark lines or bright lines using an edge detection method, the altered ID card 10 can be suitably determined to be a fake ID card 10.

[0065] More specifically, regarding the image of the ID card 10, an image of the range r1 that crosses the contour portion of the background area R can be extracted, and the brightness change of pixels along the crossing direction (left-right direction in this embodiment) can be used as edge values ​​for the aforementioned discrimination. For example, the dark lines and bright lines appear as the maximum value of the absolute value of the edge value, so this maximum value can be used as the discrimination value, and the discrimination value can be compared with a threshold value.

[0066] Furthermore, in this embodiment, the brightness image 100 is subjected to the determination of positive edge mode, negative edge mode, and normal edge mode as described above. By changing the discrimination value according to these modes, the influence of the boundary between the base color area of ​​the card substrate and the background area R can be avoided, and authenticity can be determined with high accuracy.

[0067] Furthermore, in this embodiment, a counterfeit determination system 1, which determines the authenticity of an ID card 10 from an image of the ID card 10 transmitted from a user terminal 5, can be constructed using a network.

[0068] However, the present invention is not limited to the embodiments described above. For example, in this embodiment, we have illustrated the use of authenticity verification as a means of verifying identity when opening an account, but the application scenarios or purposes of the authenticity verification in this embodiment are not particularly limited.

[0069] Furthermore, in step S401 (see Figure 9), the inspection image is obtained by extracting a range r1 that crosses the left contour portion of the background region R from the image of the ID card 10. However, multiple ranges may be extracted, and the authenticity determination process described in Figure 9, etc., may be performed on each of the multiple inspection images. This improves the accuracy of authenticity determination.

[0070] Figure 13 shows an example of extracting another area from the image of ID card 10. In addition to the area r1 mentioned above, by extracting area r1' that crosses the right-hand contour of the background area R, multiple inspection images can be obtained. The inspection image extracted from area r1' can also be subjected to the authenticity determination process described in Figure 9, etc. If ID card 10 is determined to be genuine for both inspection images, the final authenticity determination result is set to true. However, the criteria for authenticity determination are not limited to this; if ID card 10 is determined to be genuine for either inspection image, the final authenticity determination result may also be set to true.

[0071] Alternatively, as indicated by the symbol r4 in Figure 13, the area traversing the contour of the background region R in the vertical direction may be extracted. In this case, the matrix M used to calculate the edge value e can be the matrix M in Figure 11(a) rotated by 90°, and when determining the edge detection mode, the brightness of both ends of the brightness image 100 in the vertical direction (the direction traversing the contour) should be compared.

[0072] Furthermore, in this embodiment, when performing brightness conversion of the inspection image in S403 (see Figure 9), the brightness value was set to the largest grayscale value among the grayscale values ​​of the R, G, and B components of the pixels in the inspection image. However, similar to known grayscale conversion methods, the brightness value may also be calculated from a weighted sum of the grayscale values ​​of the R, G, and B components. Moreover, it is also possible to set the brightness value to the grayscale value of a predetermined component selected from the R, G, and B components.

[0073] Furthermore, although the ID card 10 is a My Number Card in this embodiment, the present invention is not limited to this, and can be applied to various types of identification documents on which a facial image 101 is formed, and can be applied even if the background area R is transparent.

[0074] Preferred embodiments of the present invention have been described above with reference to the attached drawings, but the present invention is not limited to these examples. It will be obvious to those skilled in the art that various modifications or alterations can be conceived within the scope of the technical idea disclosed herein, and these will naturally also fall within the technical scope of the present invention. [Explanation of Symbols]

[0075] 1: Authenticity Verification System 3: Authenticity verification device 5: User terminal 10: ID card 100: Brightness Image 101: Face image 102: Printed matter 301: Receiving means 302: Means for determining authenticity

Claims

1. A device for determining the authenticity of an identification document on which a facial image has been formed, The system includes a means for determining authenticity, which, based on the results of edge detection performed on the image of the aforementioned identification document, determines whether or not printed material has been pasted onto the background area of ​​the face image, and if it is determined that printed material has been pasted onto the background area of ​​the face image, determines that the identification document is fake. The authenticity determination means is characterized by calculating edge values ​​that indicate the magnitude of brightness changes of pixels in the direction crossing the contour portion for an image in the range crossing the contour portion of the background region, using the maximum absolute value of the edge values ​​as the discrimination value, and performing the discrimination by comparing the discrimination value with a threshold.

2. A device for determining the authenticity of an identification document on which a facial image has been formed, The system includes a means for determining authenticity, which, based on the results of edge detection performed on the image of the aforementioned identification document, determines whether or not printed material has been pasted onto the background area of ​​the face image, and if it is determined that printed material has been pasted onto the background area of ​​the face image, determines that the identification document is fake. The authenticity determination means calculates edge values ​​indicating the magnitude of brightness changes of pixels in the direction crossing the contour portion for an image in the area crossing the contour portion of the background region, and performs the determination using the edge values. The authenticity determination means compares the brightness of both ends in the direction crossing the contour portion of the background region for an image in the range crossing the contour portion, and based on the comparison result, The edge value indicating that the brightness increases toward one of the two ends is used for the determination, The edge value indicating that the brightness decreases toward one of the aforementioned sides is used for the determination, A device for determining authenticity, characterized by its ability to determine [something].

3. The authenticity determination device according to claim 1 or 2, characterized in that it has receiving means for receiving an image of the identity verification document from a user terminal.

4. Computers, A device for determining the authenticity of an identification document on which a facial image has been formed, The system includes a means for determining authenticity, which, based on the results of edge detection performed on the image of the aforementioned identification document, determines whether or not printed material has been pasted onto the background area of ​​the face image, and if it is determined that printed material has been pasted onto the background area of ​​the face image, determines that the identification document is fake. The program for causing the authenticity determination means to function as an authenticity determination device is characterized by calculating edge values ​​that indicate the magnitude of brightness changes of pixels in the direction crossing the contour portion of an image in the range crossing the contour portion of the background region, using the maximum value of the absolute value of the edge values ​​as the discrimination value, and performing the discrimination by comparing the discrimination value with a threshold.

5. Computers, A device for determining the authenticity of an identification document on which a facial image has been formed, The system includes a means for determining authenticity, which, based on the results of edge detection performed on the image of the aforementioned identification document, determines whether or not printed material has been pasted onto the background area of ​​the face image, and if it is determined that printed material has been pasted onto the background area of ​​the face image, determines that the identification document is fake. The authenticity determination means calculates edge values ​​indicating the magnitude of brightness changes of pixels in the direction crossing the contour portion for an image in the area crossing the contour portion of the background region, and performs the determination using the edge values. The authenticity determination means compares the brightness of both ends in the direction crossing the contour portion of the background region for an image in the range crossing the contour portion, and based on the comparison result, The edge value indicating that the brightness increases toward one of the two ends is used for the determination, The edge value indicating that the brightness decreases toward one of the aforementioned sides is used for the determination, A program for functioning as a genuine / counterfeit detection device, characterized by its ability to determine [a specific value].

Images